Token Saver 75+

Automatically classifies requests to optimize cost by routing to the cheapest capable model and applies maximum output compression for 75%+ token savings.

What to consider before installing: - Do not add this skill to your system prompt or otherwise make it mandatory without a careful review. The README explicitly recommends forcing the skill into every session — that's a prompt-injection/persistence escalation and should be avoided. - Because the SKILL.md tells spawned sessions to include "ALL context," verify how your platform implements sessions_spawn. Confirm that sensitive or private context will not be sent to third-party models or logs unintentionally. - The skill references model IDs (openai/..., anthropic/..., groq/...). Map those to your environment carefully and be aware of cost implications; routing could increase usage of expensive models if misconfigured. - Test in an isolated, auditable environment first: limit the skill to user-invocable (not always-on), enable request/response logging, and monitor which models are actually invoked and what context is forwarded. - If you like the behavior, implement the protocol in a reviewed internal policy rather than blindly following the README's "mandatory" instruction. Remove or neutralize the recommendation to edit system prompts. - Consider restricting autonomous invocation for this skill (or requiring explicit human approval for spawns) until you're confident it won't leak data or escalate costs. If you want a safer path forward: ask the author for clarification on why they recommend forcing the skill into system prompts, request a version that does not require including full context in spawn tasks, and get explicit documentation on what gets forwarded to spawned models. Because the SKILL.md includes a prompt-injection signal, proceed cautiously and prefer a manual opt-in model.

Type: OpenClaw Skill Name: token-saver-75plus Version: 1.0.0 The skill is designed for token optimization and model routing, which are benign goals. However, the `SKILL.md` instructions create significant prompt injection vulnerabilities. Specifically, it instructs the agent to use `sessions_spawn` for 'ALL code generation' via `openai/gpt-5.3-codex` and for T4 strategy tasks via `anthropic/claude-opus-4-6` with the explicit instruction 'You have full tool access.' These broad capabilities, while not inherently malicious in their design, allow a malicious user prompt to coerce the agent into generating and potentially executing harmful code or performing unauthorized actions using its 'full tool access', thus posing a high risk of exploitation.